{"total":69,"rows":[{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89,"area":null},{"id":"2511.13719","title":"Scaling Spatial Intelligence with Multimodal Foundation Models","created":"2025-11-17","cited_by_count":82,"area":null},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65,"area":null},{"id":"2503.19903","title":"Scaling Vision Pre-Training to 4K Resolution","created":"2025-03-25","cited_by_count":28,"area":null},{"id":"2506.03642","title":"Spatial Understanding from Videos: Structured Prompts Meet Simulation Data","created":"2025-06-04","cited_by_count":28,"area":null},{"id":"2510.01174","title":"Code2Video: A Code-centric Paradigm for Educational Video Generation","created":"2025-10-01","cited_by_count":27,"area":null},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2601.21406","title":"Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation","created":"2026-01-29","cited_by_count":20,"area":null},{"id":"2602.07055","title":"Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?","created":"2026-02-04","cited_by_count":19,"area":null},{"id":"2502.16435","title":"Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs","created":"2025-02-23","cited_by_count":13,"area":null},{"id":"2505.20981","title":"RefAV: Towards Planning-Centric Scenario Mining","created":"2025-05-27","cited_by_count":13,"area":null},{"id":"2508.11952","title":"UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding","created":"2025-08-16","cited_by_count":10,"area":null},{"id":"2509.08757","title":"SocialNav-SUB: Benchmarking VLMs for Scene Understanding in Social Robot Navigation","created":"2025-09-10","cited_by_count":10,"area":null},{"id":"2505.24870","title":"GenSpace: Benchmarking Spatially-Aware Image Generation","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2407.05047","title":"MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning","created":"2024-07-06","cited_by_count":8,"area":null},{"id":"2507.18678","title":"Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting","created":"2025-07-24","cited_by_count":8,"area":null},{"id":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2505.23769","title":"TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models","created":"2025-05-29","cited_by_count":7,"area":null},{"id":"2512.17875","title":"Visually Prompted Benchmarks Are Surprisingly Fragile","created":"2025-12-19","cited_by_count":7,"area":null},{"id":"2603.11421","title":"ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation","created":"2026-03-12","cited_by_count":7,"area":null},{"id":"2605.08747","title":"Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents","created":"2026-05-09","cited_by_count":7,"area":null},{"id":"2604.07296","title":"OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence","created":"2026-04-08","cited_by_count":6,"area":null},{"id":"2607.10383","title":"ABot-N1: Toward a General Visual Language Navigation Foundation Model","created":"2026-07-11","cited_by_count":6,"area":null},{"id":"2509.24966","title":"Social 3D Scene Graphs: Modeling Human Actions and Relations for Interactive Service Robots","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2605.13169","title":"PanoWorld: Towards Spatial Supersensing in 360$^\\circ$ Panorama World","created":"2026-05-13","cited_by_count":5,"area":null},{"id":"2506.04897","title":"From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2506.08002","title":"Aligning Text, Images, and 3D Structure Token-by-Token","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2607.08970","title":"MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs","created":"2026-07-09","cited_by_count":4,"area":null},{"id":"2512.18028","title":"Embodied4C: Measuring What Matters for Embodied Vision-Language Navigation","created":"2025-12-19","cited_by_count":3,"area":null},{"id":"2512.20907","title":"PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding","created":"2025-12-24","cited_by_count":3,"area":null},{"id":"2605.12449","title":"LychSim: A Controllable and Interactive Simulation Framework for Vision Research","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2605.29563","title":"Planning with the Views","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2504.17833","title":"The Role of Open-Source LLMs in Shaping the Future of GeoAI","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2506.02167","title":"Fire360: A Benchmark for Robust Perception and Episodic Memory in Degraded 360-Degree Firefighting Videos","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2510.21160","title":"Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2602.04053","title":"Seeing Through Clutter: Structured 3D Scene Reconstruction via Iterative Object Removal","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2603.09896","title":"Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2605.22823","title":"Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2607.21072","title":"Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text","created":"2026-07-23","cited_by_count":2,"area":null},{"id":"2507.19891","title":"Interpretable Open-Vocabulary Referring Object Detection with Reverse Contrast Attention","created":"2025-07-26","cited_by_count":1,"area":null},{"id":"2508.17044","title":"M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2509.21388","title":"TUN3D: Towards Real-World Scene Understanding from Unposed Images","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2510.01704","title":"Holistic Order Prediction in Natural Scenes","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2510.14627","title":"GOPLA: Generalizable Object Placement Learning via Synthetic Augmentation of Human Arrangement","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2511.14086","title":"Error-Driven Scene Editing for 3D Grounding in Large Language Models","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2603.06561","title":"EgoReasoner: Learning Egocentric 4D Reasoning via Task-Adaptive Structured Thinking","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.21046","title":"SpatialFly: Implicit 3D Prior-Guided Visual Reparameterization for Continuous UAV Vision-and-Language Navigation","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2609.19554","title":"VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2507.06993","title":"IMAIA: Interactive Maps AI Assistant for Travel Planning and Geo-Spatial Intelligence","created":"2025-07-09","cited_by_count":0,"area":null},{"id":"2512.04568","title":"Prompt2Craft: Generating Functional Craft Assemblies with LLMs","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2601.09613","title":"CogRail: Benchmarking VLMs in Cognitive Intrusion Perception for Intelligent Railway Transportation Systems","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2602.18630","title":"Lost in Instructions: Study of Blind Users' Experiences with DIY Manuals and AI-Rewritten Instructions for Assembly, Operation, and Troubleshooting of Tangible Products","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2603.08096","title":"TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.09961","title":"BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.19209","title":"Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.26690","title":"SpatialPoint: Spatial-aware Point Prediction for Embodied Localization","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2605.20733","title":"Sketch2MinSurf: Vision-Language Guided Generation of Editable Minimal Surfaces from Hand-Drawn Sketches","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2607.02921","title":"R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.12429","title":"More Than Where You Are: Learning Semantics, Structure, and Geometry from Cross-View Localization","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.15491","title":"Trajectory-aware Cross-view Geo-localization with Sequential Observations","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.09147","title":"RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.15788","title":"ChainSpace: A Chained-Reasoning Paradigm for Spatial Intelligence","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.22800","title":"Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulation","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.24935","title":"A Lightweight Multimodal Vision-Language Framework for Early-Stage Anatomical Green Fruit Classification in Commercial Orchards","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.06629","title":"Physico-Geospatial Grounded Scene Interpretation for Mobile Robotics","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.20475","title":"SenseFuse: Label-Free Fusion of Image and Shape Encoders for Open-Vocabulary 3D Instance Segmentation","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.39195","title":"Uruqi: Learning Spatial Cognition from Visual Experience","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.15782","title":"Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.17640","title":"MemAct: Streaming Spatial Understanding with Memory and Active Exploration","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}